Commits · 1dc8a70b6d4e8ba4e139f1ddb86a166694f42f21 · OpenDAS / vllm_cscc

07 Aug, 2025 4 commits

[Attention] Support multiple attention metadata builders per kv_cache_spec +... · 1dc8a70b

Lucas Wilkinson authored Aug 06, 2025


[Attention] Support multiple attention metadata builders per kv_cache_spec  + proper local attention no hybrid kv cache fix (#21588)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

1dc8a70b

Support encoder_only attention for FlexAttention (#22273) · f825c6bd
Maximilien de Bayser authored Aug 06, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
```
f825c6bd

Fix trtllm-gen attention env and add attention sink (#22378) · 9a3835aa

Lain authored Aug 06, 2025


Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Lain <fusiyuan2000@hotmail.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

9a3835aa

[v1] - Mamba1 Attention Metadata (#21249) · 46a13949
Asaf Joseph Gardin authored Aug 07, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
46a13949

06 Aug, 2025 3 commits

[gpt-oss] Enhance error msg on attention sink init (#22335) · 31f5dc5b

Yongye Zhu authored Aug 06, 2025


Signed-off-by: simon-mo <xmo@berkeley.edu>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>

31f5dc5b

[gpt-oss] flashinfer attention sink init (#22330) · 90ec0069

Yongye Zhu authored Aug 05, 2025


Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>

90ec0069

Add attention sink in attention backends (#22320) · 6e209243

Woosuk Kwon authored Aug 05, 2025


Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
Co-authored-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Hongxia Yang <62075498+hongxiayang@users.noreply.github.com>
Co-authored-by: Minseok Lee <47620120+minseokl@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>

6e209243

05 Aug, 2025 3 commits
- [V1] port xformers backend to v1 (#21342) · 469b3ffa
  Giancarlo Delfin authored Aug 05, 2025
```
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
```
  469b3ffa
- [NVIDIA] Support Flashinfer TRT-LLM Prefill Attention Kernel (#22095) · 83156c7b
  elvischenv authored Aug 05, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  83156c7b
- [Bugfix] Misaligned params in TreeAttentionImpl (#22226) · cdfd6871
  Cyrus Leung authored Aug 05, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cdfd6871
04 Aug, 2025 2 commits
- Add tree attention backend for v1 (part 1) (#20401) · aa7012eb
  Giancarlo Delfin authored Aug 03, 2025
```
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
```
  aa7012eb
- [fix] fix correct assertion syntax error in attention utils. (#22154) · e27d25a0
  ZiTian.Zhao authored Aug 04, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  e27d25a0
02 Aug, 2025 3 commits
- [V1] [Hybrid] Validate compatibility of attention backend batch reordering at init time (#21557) · 4abfd879
  Thomas Parnell authored Aug 02, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  4abfd879
- [Attention][DBO] Add support for "splitting" the CommonAttentionMetadata (#21153) · 0edaf752
  Sage Moore authored Aug 01, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  0edaf752
- [V1][CUDA] Full cudagraph support for FlashInfer (#21367) · 23322431
  fhl2000 authored Aug 02, 2025
  
  23322431
01 Aug, 2025 2 commits
- [Bugfix] Check NVIDIA artifactory is accessible before using flashinfer cubin kernels (#21893) · f81c1bb0
  Michael Goin authored Aug 01, 2025
  
  f81c1bb0
- [BugFix] fix: aot passes kvcache dtype information (#19750) · e1a7fe4a
  Mickaël Seznec authored Aug 01, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
```
  e1a7fe4a
31 Jul, 2025 1 commit
- [UX] Rename CUTLASS_MLA_VLLM_V1 to CUTLASS_MLA (#21966) · 61445453
  Michael Goin authored Jul 30, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  61445453
30 Jul, 2025 2 commits
- Override attention metadata for fast prefill in some KV sharing setups (#21590) · ad510309
  Yong Hoon Shin authored Jul 30, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  ad510309
- [v1][attention] Support Hybrid Allocator + FlashInfer (#21412) · 555e7225
  Chen Zhang authored Jul 29, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  555e7225
29 Jul, 2025 1 commit
- [Bugfix] Fix workspace buffer None issue for Flashinfer TRTLLM Backend (#21525) · 58b11b24
  elvischenv authored Jul 29, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  58b11b24
28 Jul, 2025 1 commit
- [v1][mamba] Added mamba_type into MambaSpec (#21715) · a6c05028
  Asaf Joseph Gardin authored Jul 28, 2025
```
Signed-off-by: asafg <asafg@ai21.com>
Co-authored-by: asafg <asafg@ai21.com>
```
  a6c05028
26 Jul, 2025 1 commit

Support encoder-only models without KV-Cache (#21270) · 1cd6eaba

Maximilien de Bayser authored Jul 26, 2025


Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

1cd6eaba

25 Jul, 2025 1 commit

[ROCm][AITER] Enable fp8 kv cache on rocm aiter backend. (#20295) · b3caeb82

who who who authored Jul 25, 2025


Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: amd-ruitang3 <Rui.Tang2@amd.com>
Co-authored-by: amd-ruitang3 <Rui.Tang2@amd.com>

b3caeb82

24 Jul, 2025 2 commits
- update flashinfer to v0.2.9rc1 (#21485) · 2dd72d23
  weiliang authored Jul 25, 2025
```
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
```
  2dd72d23
- [Attention] Optimize FlashInfer MetadataBuilder Build call (#21137) · 61b8cea3
  Lucas Wilkinson authored Jul 24, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  61b8cea3
21 Jul, 2025 1 commit

[Attention] Clean up iRoPE in V1 (#21188) · 304dce7e

Lucas Wilkinson authored Jul 21, 2025


Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

304dce7e

20 Jul, 2025 1 commit
- [TPU] support fp8 kv cache quantization (#19292) · 3a1d8940
  Chengji Yao authored Jul 19, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  3a1d8940
19 Jul, 2025 3 commits
- [V0 Deprecation] Deprecate BlockSparse Attention & Phi3-Small (#21217) · 752c6ade
  Woosuk Kwon authored Jul 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  752c6ade
- [BugFix] Fix potential cuda-graph IMA (#21196) · 59f93530
  Lucas Wilkinson authored Jul 19, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  59f93530
- [Core] Support Local Chunked Attention for Hybrid KV Cache (#19351) · 9a9fda14
  Lucia Fang authored Jul 19, 2025
```
Signed-off-by: Lucia Fang <fanglu@fb.com>
Signed-off-by: Lu Fang <fanglu@meta.com>
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Lu Fang <fanglu@meta.com>
```
  9a9fda14
18 Jul, 2025 2 commits
- [Attention] Make local attention backend agnostic (#21093) · 89cab4d0
  Lucas Wilkinson authored Jul 18, 2025
  
  89cab4d0
- [Bugfix] Fix the tensor non-contiguous issue for Flashinfer TRT-LLM backend... · 8dfb45ca
  elvischenv authored Jul 18, 2025
```
[Bugfix] Fix the tensor non-contiguous issue for Flashinfer TRT-LLM backend attention kernel (#21133)
```
  8dfb45ca
17 Jul, 2025 2 commits
- [Attention] Refactor attention metadata builder interface (#20466) · 76b49444
  Lucas Wilkinson authored Jul 17, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  76b49444
- Remove torch_xla.tpu.version() from pallas.py. (#21065) · 72ad2735
  QiliangCui authored Jul 16, 2025
```
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
```
  72ad2735
16 Jul, 2025 3 commits
- [TPU] fix kv_cache_update kernel block size choosing logic (#21007) · 85431bd9
  Chengji Yao authored Jul 15, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  85431bd9
- [CI] update typos config for CI pre-commit and fix some spells (#20919) · 1eb2b9c1
  Peter Pan authored Jul 16, 2025
```
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
```
  1eb2b9c1
- [Nvidia] Integrate SM100 cudnn prefill API to MLA prefill (#20411) · 30800b01
  Elfie Guo authored Jul 15, 2025
```
Signed-off-by: Elfie Guo <elfieg@nvidia.com>
Co-authored-by: Elfie Guo <eflieg@nvidia.com>
```
  30800b01
15 Jul, 2025 2 commits
- [TPU] Optimize kv cache update kernel (#20415) · c586b556
  Yifei Teng authored Jul 15, 2025
```
Signed-off-by: Yifei Teng <tengyifei88@gmail.com>
```
  c586b556
- SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP (#20769) · 8cdc3712
  Alexander Matveev authored Jul 14, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  8cdc3712